Uses of Package
ai.beestream.jitnn.nn.models
Packages that use ai.beestream.jitnn.nn.models
Package
Description
Complete models: ResNet, MobileNetV2, GPT-2, a Llama-style decoder, BERT, a VAE, DCGAN, U-Net and
character RNNs, and the embedding models word2vec, doc2vec and GloVe.
-
Classes in ai.beestream.jitnn.nn.models used by ai.beestream.jitnn.nn.modelsClassDescriptionA BERT-style encoder for masked language modelling: token and learned position embeddings with LayerNorm, post-LayerNorm blocks of bidirectional attention (with an additive padding mask) and a GELU MLP of 4 x dim, and an MLM head (dense, GELU, LayerNorm, then the token embedding as the decoder with its own bias).How a document's words are predicted.A GPT-2 style decoder: token and learned position embeddings, pre-LayerNorm blocks of causal multi-head attention and a GELU (tanh form) MLP of 4 x dim, a final LayerNorm, and logits from the token embedding (tied weights).A Hugging Face model directory:
config.jsonand the weights inmodel.safetensorsor in shards listed bymodel.safetensors.index.json.A Llama-style decoder: token embedding, pre-RMSNorm blocks of causal attention with rotary position embedding (rotate-half form) and a SwiGLU feed-forward, a final RMSNorm and an untied output projection; no biases.Reconstruction probabilities [B, in] and the latent mean and log-variance [B, latent].Which word predicts which.